WO2012070880A2 - Content-providing method and system - Google Patents

Content-providing method and system Download PDF

Info

Publication number
WO2012070880A2
WO2012070880A2 PCT/KR2011/009014 KR2011009014W WO2012070880A2 WO 2012070880 A2 WO2012070880 A2 WO 2012070880A2 KR 2011009014 W KR2011009014 W KR 2011009014W WO 2012070880 A2 WO2012070880 A2 WO 2012070880A2
Authority
WO
WIPO (PCT)
Prior art keywords
content
time interval
type cluster
representative type
cluster
Prior art date
Application number
PCT/KR2011/009014
Other languages
English (en)
French (fr)
Other versions
WO2012070880A3 (en
Inventor
Hyung-Dong Lee
Seung-Taek Park
Hee-Seon Park
Hae-Dong Yeo
Original Assignee
Samsung Electronics Co., Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Samsung Electronics Co., Ltd. filed Critical Samsung Electronics Co., Ltd.
Priority to EP11842778.0A priority Critical patent/EP2643807A4/en
Priority to CN201180056996.2A priority patent/CN103229169B/zh
Priority to JP2013539779A priority patent/JP5830545B2/ja
Publication of WO2012070880A2 publication Critical patent/WO2012070880A2/en
Publication of WO2012070880A3 publication Critical patent/WO2012070880A3/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/335Filtering based on additional data, e.g. user or group profiles
    • G06F16/337Profile generation, learning or modification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Definitions

  • the present invention relates generally to a content-providing method and system, and more particularly, to a content-providing method and system for effectively supplying a customized service by classifying data regarding usage behavior of users into representative content types, analyzing the representative types, and identifying time intervals in which the representative types consistently occur, without having to use user identification information.
  • An aspect of the present invention provides a content-providing method, a content-providing system, and a computer-readable recording medium for recording a program for performing the method.
  • Embodiments of the invention provide content-providing method and system for effectively supplying a customized service by classifying data regarding usage behavior of users into representative content types, analyzing the representative types, and identifying time intervals in which the representative types consistently occur, without having to use user identification information.
  • FIG. 1 is a block diagram of a content-providing system according to an embodiment of the present invention.
  • FIG. 2 is a detailed block diagram of the content-providing system of FIG. 1.
  • FIG. 3 is a diagram illustrating an operation method of a time interval identifier according to an embodiment of the present invention.
  • FIG. 4 is a more detailed block diagram of the content-providing system of FIG. 1.
  • FIG. 5 is a diagram illustrating an example of content being provided by the content-providing system of FIG. 4.
  • FIG. 6 is a flowchart of a content-providing method according to an embodiment of the present invention.
  • FIG. 7 is a detailed flowchart illustrating operations of identifying a representative type cluster of FIG. 6.
  • FIG. 8 is a detailed flowchart illustrating operations of mapping a representative type cluster to a time interval.
  • FIG. 9 is a detailed flowchart illustrating a content-providing method according to an embodiment of the present invention.
  • a content-providing method including identifying a representative type cluster by clustering content related to behavioral data which represents a use history of a user, according to types; mapping the representative type cluster to a time interval; and storing the representative type cluster and the time interval.
  • a content-providing system including a use history analyzer for identifying a representative type cluster by clustering content related to behavioral data which represents a use history of a user, according to type of the content; and a time interval identifier for mapping the representative type cluster on a time interval and for storing the representative type cluster and the time interval.
  • a computer-readable recording medium for having recorded thereon a program for performing the content-providing method.
  • FIG. 1 is a block diagram illustrating a content-providing system 100 according to an embodiment of the present invention.
  • the content-providing system 100 includes a use history analyzer 110 and a time interval identifier 120.
  • the use history analyzer 110 performs clustering content related to behavioral data of a user which represents a use history of the user, according to types, thereby identifying a representative type cluster.
  • a type, according to the present invention may include a taste (or preference) of an unidentified user or user group.
  • behavioral data regarding children’s user group taste may relate to animation-related content
  • behavioral data regarding housewives’ user group taste may relate to romance-related content, which is described in more detail below with reference to FIG. 5.
  • the use history analyzer 100 is configured to extract metadata of content related to behavioral data and to perform clustering of the extracted metadata of content according to types, thus generating cluster types which include the content as members. Then, the use history analyzer 100 is configured to identify a representative type cluster from among the cluster types, which includes content amounting to a predetermined threshold or higher as members.
  • a user who is an unidentified user, may be a person, a group, or all users of a specific system.
  • Behavioral data may represent a use history of a user with regard to a service item provided by the content-providing system 100.
  • the service item may include a customized content-recommendation service based on a viewing history in a Video On Demand (VOD) service, selection of a TV program at an airport, preparation of a customized promotion list based on major groups of customers (housewives, dual-income families, single-person families) at a shopping center or a market place according to time intervals, and customized advertisement and environment management (background music) based on tastes of major customers (students, commuters, general public) according to time intervals at a subway station.
  • VOD Video On Demand
  • the service item is not limited thereto.
  • the use history may largely include a viewing history or a purchase history of content.
  • the use history may also include various behaviors such as bookmarks, evaluations, and Internet connection sharing, which indicate a preference for specific content.
  • the use history may include all interactions of a user with regard to service items such as a TV viewing history, a VOD viewing history, a music listening history, a product purchase history, item clicking, bookmarks, and the like.
  • the time interval identifier 120 performs mapping of a identified representative type cluster to a time interval and stores the representative type cluster and the mapped time interval.
  • the time interval identifier 120 divides behavioral data into time intervals and extracts metadata of content related to behavioral data in one time interval from among the time intervals. Then, the time interval identifier 120 compares the extracted metadata of the content with metadata of content members in the representative type cluster so as to determine their similarity. Based on the similarity, the time interval identifier 120 is configured to perform mapping of the content in the one time interval to the representative type cluster.
  • the behavioral data may be divided into time interval units which are predetermined according to a use pattern.
  • the time interval identifier 120 is configured to delete a representative type cluster in which a probability of cluster mapping is a threshold or less, based on a probability of cluster mapping of content, in one time interval, which are mapped respectively to the representative type cluster. Furthermore, if the entire representative type cluster has a probability which is a threshold or less, the time interval identifier 120 is be configured to delete the one time interval.
  • time interval identifier 120 is configured to prioritize respectively a representative type cluster based on a probability of cluster mapping.
  • the content-providing system 100 deals with a technology for detecting a time interval which shows a consistent viewing taste of a user or a group of users at a viewing time, in an apparatus in which a user is not identified.
  • a service for detecting a time interval for certain consistent preferences in an apparatus such as a TV used by a group of users may be used.
  • TV users do not normally provide identification information, it is difficult to accurately identify a current viewing user. Additionally, as several users may watch TV together, it is also difficult to provide a customized service.
  • a TV viewing pattern may change according to time, and some viewing time intervals may have characteristics which are consistent and definitely different from other viewing time intervals.
  • a customized service system may supply an accurate customized service of content in a specific time interval, by using such characteristics without having to identify a user.
  • FIG. 2 is a detailed block diagram of the content-providing system of FIG. 1.
  • the content-providing system 100 includes a use history managing unit 210, a content and metadata managing unit 230, the use history analyzer 110, and the time interval identifier 120.
  • the content-providing system 100 further includes a use history storage unit 220 connected to the use history managing unit 210, and a content and metadata storage unit 240 connected to the content and metadata managing unit 230.
  • the use history managing unit 210 collects behavioral data from a user apparatus and stores the behavioral data with time information.
  • the user apparatus may be a client apparatus, for example, a TV or a Personal Computer (PC) having an Internet connection.
  • the content-providing system 100 may be a server apparatus for supplying a customized service to the user apparatus.
  • the use history managing unit 210 stores and manages behavioral data in an order of time.
  • the use history managing unit 210 stores a corresponding user apparatus Identification (ID), information regarding content purchased at a specific time from the corresponding user apparatus, and time information of the purchase in such a format as ⁇ Device id, Content id, Timestamp>.
  • ID user apparatus Identification
  • the use history managing unit 210 stores all records by using an ID of the corresponding user apparatus. For example, in a shopping mall, the use history managing unit 210 stores entire purchase-related behaviors of all personal users with time information.
  • the content and metadata managing unit 230 manages service items and metadata such as content, products, and services which are provided by a corresponding user apparatus.
  • the content and metadata managing unit 230 also extracts and manages characteristics information about each content. For example, by using content metadata such as a title, caption, actors, and genre as features, the characteristics information may be expressed in a feature vector format.
  • the use history analyzer 110 configures a cluster by classifying content according to representative types, based on analysis of the content related to a use history of a specific user apparatus. Specifically, the use history analyzer 110 performs clustering content of all user behavioral data stored in each user apparatus. Clustering is performed by classifying similar content into groups.
  • the use history analyzer 110 performs grouping of content with similar characteristics by using characteristics information, i.e., metadata, which is extracted from the content and metadata managing unit 230 according to each content.
  • the use history analyzer 110 measures a distance between content, and classifies content within a close distance into one group.
  • the use history analyzer 110 uses a representative k-means algorithm for the clustering, and may also use a cosine value or a Euclidean Distance between feature vectors, in order to measure a distance which represents a similarity between content.
  • a method of clustering is not limited thereto, and various methods known to those of ordinary skill in the art may be used to perform the clustering.
  • Such a type of cluster may be characterized by a collection of content with a consistent taste or preference.
  • Related content used by a plurality of users may be one type of cluster.
  • Content used by one user may also be classified into several cluster types.
  • the use history analyzer 110 identifies a representative type cluster which includes content, as a member, the number of which is a predetermined threshold or higher.
  • the time interval identifier 120 performs mapping of the representative type cluster to a time interval, which is analyzed in the use history analyzer 110. Referring to FIG. 3A, a method of performing the mapping is described in detail.
  • FIG. 3 is a diagram illustrating a method of operation of the time interval identifier 120 according to an embodiment of the present invention.
  • ‘A’, ‘B’, ‘C’, and ‘D’ respectively indicate identified representative type clusters, ‘A’, ‘B’, ‘C’, and ‘D’.
  • the time interval identifier 120 performs mapping of a representative type cluster to a time interval.
  • the time interval identifier 120 divides a use history, i.e., behavioral data, into predetermined time interval units according to a use pattern.
  • the time interval identifier 120 divides a day into time intervals, or accumulates data in time intervals according to a day of the week or for a long period of time.
  • the time interval identifier 120 performs mapping of a representative type cluster to each time interval, based on cluster membership of content in a time interval, i.e., a probability of cluster mapping.
  • the time interval identifier 120 performs mapping of one representative type cluster to several time intervals, in case that users having the same taste emerge in two time intervals.
  • the representative type cluster ‘C’ is mapped to two time intervals from 9 to 10 o’clock and from 13 to 14 o’clock.
  • time interval identifier 120 performs mapping of one time interval to several representative type clusters.
  • representative type clusters may be prioritized in an order from the most appropriate representative type cluster, according to a ratio of content in the corresponding time interval.
  • the time interval identifier 120 excludes a representative type cluster in which a probability of cluster mapping is less than a specific threshold.
  • the time interval identifier 120 selects ‘A’ and ‘B’ and excludes ‘D’. If a mapping probability of all representative type clusters is less than the threshold, that is, in a time interval with a mixed type (or taste), the time interval identifier 120 excludes the corresponding time interval.
  • a time interval which is identified as such may be applied to various customized services. Services may be further improved by providing services based on characteristics data of an identified representative type cluster, rather than by employing characteristics data only in one time interval.
  • FIG. 4 is a more detailed block diagram of the content-providing system of FIG. 1.
  • the content-providing system 100 includes the use history managing unit 210, the use history storage unit 220, the content and metadata managing unit 230, the content and metadata storage unit 240, the use history analyzer 110, the time interval identifier 120, and a providing unit 410.
  • the use history managing unit 210, the use history storage unit 220, the content and metadata managing unit 230, the content and metadata storage unit 240, the use history analyzer 110, and the time interval identifier 120 which are the same as those of FIG. 2, and thus, will not be repeatedly described here.
  • the providing unit 410 provides content which is determined according to a representative type cluster mapped to a time interval.
  • the content provided by the providing unit 410 includes service items such as customized services, customized advertisements, and the like.
  • the providing unit 410 provides content which is determined based on a representative type cluster having a highest priority, or sequentially provides content which is determined by using respective characteristics of prioritized representative type clusters.
  • providing of content may include recommendation of content.
  • the providing unit 410 when a recommended time interval is mapped to only one representative type cluster, the providing unit 410 generates a recommendation in a recommended time interval based on a profile of the corresponding cluster. In such a case, even when a relatively short viewing history is in the corresponding time interval, several different viewing histories with similar tastes in the representative type cluster may be used, thus obtaining a stable recommendation result.
  • the providing unit 410 provides a recommendation to be proportional to a probability of membership to a respective type cluster.
  • the providing unit 410 provides a recommendation based on a profile of the representative type cluster ‘A’ at a probability of five-ninths (5/9), and may provide a recommendation based on a profile of the representative type cluster ‘B’ at a probability of four-ninths (4/9).
  • a result of the recommendation may be basically different from a result obtained by mixing profiles of ‘A’ and ‘B’ and recommending the mixed profiles.
  • at least four-ninths (4/9) of users may always be favorable to the recommendation result provided by the providing unit 410.
  • the content-providing system 100 identifies and extracts a time interval which is consistently differentiated from other time intervals so as to provide an effective customized service, when an apparatus is used by several users, as in a family device, and when personal identification information is not provided.
  • an apparatus such as Internet TV, it is rare to provide identification information about a respective user during viewing of VOD content, and sometimes, it is impossible to provide identification information.
  • the content-providing system 100 may provide a basis of supplying an effective customized service by analyzing viewing history data, which is accumulated without user identification information, according to representative types and by identifying a time interval in which the respective representative types consistently occur. Furthermore, through a time interval in which a representative type consistently occurs in the present invention, the content-providing system 100 enhances user satisfaction, and thus, promote additional consumption of content via recommendation of content, and may also attract users’ attention, and thus, improve advertisement effects via customized advertisements.
  • FIG. 5 is a diagram illustrating an example of content being provided by the content-providing system of FIG. 4.
  • the providing unit 410 recommends animation content in the early evening, based on a viewing history related to a children’s user group tastes.
  • the providing unit 410 also recommends romance-related content in the morning, based on a viewing history related to housewives’ user group tastes.
  • Conventional content-providing systems may erroneously recommend content based on a mixed viewing history of several users and violent action programs may be recommended to children due to the to parents’ viewing history of action movies, or animation content for children may be recommended to adults, thereby decreasing user satisfaction. Additionally, when a user who prefers comedies and another user who prefers crime movies view movies together, both users may be unsatisfied by the recommendation of a dark comedy, as a result of mere mixing of profiles.
  • a recommendation based on a time interval which is extracted depending on types in the content-providing system 100 according to an embodiment of the present invention, may be a favorable result for each target user or user group.
  • FIGs. 6 through 9 a content-providing method according to an embodiment of the present invention is described.
  • the content-providing method is the same as the operation of the content-providing system 100 of FIGS. 1 through 4, the method will be described briefly.
  • FIG. 6 is a flowchart illustrating a content-providing method according to an embodiment of the present invention.
  • Step 610 content, related to behavioral data which represents a use history of a user, is clustered according to types, thus identifying a representative type cluster.
  • Step 620 the identified a representative type cluster is mapped to a time interval.
  • Step 630 the mapped representative type cluster and the time interval are stored.
  • Step 601 the identifying of a representative type cluster in Step 601 and the mapping of the identified a representative type cluster to a time interval in Step 602 are described in more detail.
  • FIG. 7 is a detailed flowchart illustrating operations for identifying a representative type cluster in FIG. 6.
  • Step 710 metadata of content related to behavioral data is extracted.
  • Step 702 the extracted metadata of the content is clustered according to types so that a candidate cluster type which includes the content as members is generated.
  • the candidate cluster type is designated as a representative type cluster when the number of content members reaches a predetermined threshold.
  • FIG. 8 is a detailed flowchart illustrating operations of the mapping of a representative type cluster to a time interval.
  • Step 810 the behavioral data are divided into time intervals.
  • Step 820 metadata of content related to behavioral data in one time interval from among the time intervals is extracted.
  • Step 830 the metadata of the extracted content is compared with metadata of content members in a representative type cluster to determine a similarity.
  • Step 840 based on the similarity, the content in the one time interval is mapped to the representative type cluster.
  • FIG. 9 is a flowchart illustrating the content-providing method according to an embodiment of the present invention.
  • FIG. 9 illustrates a method of providing a service of recommending customized content based on a viewing history in a VOD service supplied from a TV or a PC having an Internet connection.
  • a method of providing content is not limited thereto.
  • Step 910 characteristics of respective content in an entire viewing history are extracted.
  • the characteristics of the respective content is metadata of the respective content.
  • Step 920 a viewing history is grouped through clustering based on a similarity between the content characteristics, and a representative type cluster is identified when the number of content members reaches a threshold.
  • Step 930 characteristics of the content according to time interval units are extracted.
  • Step 940 the respective time intervals are mapped to the representative type cluster.
  • Step 950 a time interval, mapped to a representative type cluster, which has a cluster mapping probability above a threshold value, is stored.
  • the above-described embodiments of the present invention can also be embodied as computer-readable codes on a non-transitory computer-readable recording medium.
  • the computer-readable recording medium is any data storage device that can store data or software components that include instructions or code that can be read by a computer system. Examples of the computer-readable recording medium include Read-Only Memory (ROM), Random-Access Memory (RAM), Compact Disk (CD)-ROMs, magnetic tapes, floppy disks, optical data storage devices, and carrier waves (such as data transmission through the Internet).
  • the computer-readable recording medium can also be distributed over network coupled computer systems so that the computer-readable code is stored and performed in a distributed fashion. Also, functional programs, codes, and code segments for implementing a content-providing method can be easily implemented by programmers of ordinary skill in the art to which the present invention pertains.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Information Transfer Between Computers (AREA)
PCT/KR2011/009014 2010-11-25 2011-11-24 Content-providing method and system WO2012070880A2 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP11842778.0A EP2643807A4 (en) 2010-11-25 2011-11-24 METHOD AND SYSTEM FOR CONTENT PROVIDING
CN201180056996.2A CN103229169B (zh) 2010-11-25 2011-11-24 内容提供方法和系统
JP2013539779A JP5830545B2 (ja) 2010-11-25 2011-11-24 コンテンツ提供方法及びそのシステム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2010-0118105 2010-11-25
KR1020100118105A KR101802332B1 (ko) 2010-11-25 2010-11-25 컨텐츠 제공 방법 및 그 시스템

Publications (2)

Publication Number Publication Date
WO2012070880A2 true WO2012070880A2 (en) 2012-05-31
WO2012070880A3 WO2012070880A3 (en) 2012-10-04

Family

ID=46127319

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2011/009014 WO2012070880A2 (en) 2010-11-25 2011-11-24 Content-providing method and system

Country Status (6)

Country Link
US (1) US9465863B2 (ja)
EP (1) EP2643807A4 (ja)
JP (1) JP5830545B2 (ja)
KR (1) KR101802332B1 (ja)
CN (1) CN103229169B (ja)
WO (1) WO2012070880A2 (ja)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017092342A1 (zh) * 2015-12-02 2017-06-08 乐视控股(北京)有限公司 一种推荐方法和装置
CN111277859A (zh) * 2020-01-15 2020-06-12 腾讯科技(深圳)有限公司 配乐获取方法、装置、计算机设备和存储介质

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6015162B2 (ja) * 2012-06-27 2016-10-26 ソニー株式会社 端末装置、情報処理システム、情報処理方法およびプログラム
US9607025B2 (en) 2012-09-24 2017-03-28 Andrew L. DiRienzo Multi-component profiling systems and methods
EP2840514A1 (en) * 2013-08-21 2015-02-25 Thomson Licensing Method and device for assigning time information to a multimedia content
CN104661055A (zh) * 2013-11-21 2015-05-27 中兴通讯股份有限公司 一种业务推荐方法及装置
CN105320702B (zh) * 2014-08-04 2019-02-01 Tcl集团股份有限公司 一种用户行为数据的分析方法、装置及智能电视
CN104918070A (zh) * 2015-06-02 2015-09-16 四川九天揽月文化传媒有限公司 一种基于智能电视的视频节目推送系统及推送方法
CN106131703A (zh) * 2016-06-28 2016-11-16 青岛海信传媒网络技术有限公司 一种视频推荐的方法和终端
US20180211270A1 (en) * 2017-01-25 2018-07-26 Business Objects Software Ltd. Machine-trained adaptive content targeting
CN108804462B (zh) * 2017-05-03 2021-08-27 腾讯科技(深圳)有限公司 一种广告推荐方法、装置及服务器
CN107071578B (zh) * 2017-05-24 2019-11-22 中国科学技术大学 Iptv节目推荐方法
WO2019058717A1 (ja) * 2017-09-22 2019-03-28 シャープ株式会社 情報処理装置、表示システム、コンテンツ推奨方法、および制御プログラム
WO2019159288A1 (ja) * 2018-02-15 2019-08-22 楽天株式会社 情報処理システム、情報処理方法、及びプログラム
CN109146474A (zh) * 2018-07-18 2019-01-04 阿里巴巴集团控股有限公司 一种支付限额定制方法及装置
CN113377775B (zh) * 2021-06-21 2024-02-02 特赞(上海)信息科技有限公司 信息处理方法及装置

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060136528A1 (en) 2004-12-20 2006-06-22 Claria Corporation Method and device for publishing cross-network user behavioral data

Family Cites Families (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010013009A1 (en) * 1997-05-20 2001-08-09 Daniel R. Greening System and method for computer-based marketing
JP3844901B2 (ja) * 1999-02-26 2006-11-15 株式会社東芝 電子番組ガイド受信システム
WO2002010984A2 (en) * 2000-07-21 2002-02-07 Triplehop Technologies, Inc. System and method for obtaining user preferences and providing user recommendations for unseen physical and information goods and services
WO2002042959A2 (en) 2000-11-22 2002-05-30 Koninklijke Philips Electronics N.V. Television program recommender with interval-based profiles for determining time-varying conditional probabilities
US20040181604A1 (en) 2003-03-13 2004-09-16 Immonen Pekka S. System and method for enhancing the relevance of push-based content
US20050222987A1 (en) * 2004-04-02 2005-10-06 Vadon Eric R Automated detection of associations between search criteria and item categories based on collective analysis of user activity data
JP2005318343A (ja) 2004-04-30 2005-11-10 Sony Corp 視聴覚情報データ処理装置
JP2005352754A (ja) * 2004-06-10 2005-12-22 Sharp Corp 情報ナビゲーション装置、方法、プログラム、及び記録媒体
US8281037B2 (en) 2005-01-03 2012-10-02 Orb Networks, Inc. System and method for delivering content to users on a network
US8073866B2 (en) * 2005-03-17 2011-12-06 Claria Innovations, Llc Method for providing content to an internet user based on the user's demonstrated content preferences
US7340060B2 (en) * 2005-10-26 2008-03-04 Black Box Intelligence Limited System and method for behavioural modelling
US7792815B2 (en) * 2006-03-06 2010-09-07 Veveo, Inc. Methods and systems for selecting and presenting content based on context sensitive user preferences
US8407164B2 (en) * 2006-10-02 2013-03-26 The Trustees Of Columbia University In The City Of New York Data classification and hierarchical clustering
KR101351022B1 (ko) 2007-03-05 2014-01-13 엘지전자 주식회사 방송 신호 송수신 방법 및 방송 신호 수신 장치
JP2008233295A (ja) * 2007-03-19 2008-10-02 Kddi Corp 広告配信装置、広告配信方法およびプログラム
CN101079063A (zh) * 2007-06-25 2007-11-28 腾讯科技(深圳)有限公司 一种基于场景信息推送广告的方法、系统及设备
JP2010531626A (ja) * 2007-06-25 2010-09-24 ジャンプタップ,インコーポレイテッド モバイルコンテンツの一部に関連するコンテキストデータ及び挙動データに基づくモバイル通信設備へのコンテンツの提供
JP5251039B2 (ja) 2007-08-23 2013-07-31 ソニー株式会社 情報処理装置、情報処理方法、およびプログラム
JP2009239686A (ja) 2008-03-27 2009-10-15 Hitachi Ltd 放送受信システム、ホームゲートウェイ装置及び放送受信端末装置
US7979426B2 (en) * 2008-06-05 2011-07-12 Samsung Electronics Co., Ltd. Clustering-based interest computation
US20100011020A1 (en) * 2008-07-11 2010-01-14 Motorola, Inc. Recommender system
JP5079642B2 (ja) 2008-09-16 2012-11-21 日本電信電話株式会社 履歴処理装置、履歴処理方法および履歴処理プログラム
KR20100043639A (ko) 2008-10-20 2010-04-29 주식회사 대우일렉트로닉스 사용자 식별 기반의 방송 수신 제어 장치 및 방법
KR20100055712A (ko) * 2008-11-18 2010-05-27 한국전자통신연구원 개인 맞춤형 컨텐트 추천 방법 및 장치
KR101054088B1 (ko) * 2009-02-25 2011-08-03 한국과학기술원 협업 필터링을 이용한 사용자 맞춤형 아이피 티브이 프로그램 자동 추천 방법
WO2010119807A1 (ja) * 2009-04-13 2010-10-21 シャープ株式会社 番組検索装置、情報表示装置およびデジタル放送受信装置
US8468161B2 (en) * 2009-07-14 2013-06-18 Hewlett-Packard Development Company, L.P. Determining a seasonal effect in temporal data
US9836482B2 (en) * 2009-12-29 2017-12-05 Google Inc. Query categorization based on image results

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060136528A1 (en) 2004-12-20 2006-06-22 Claria Corporation Method and device for publishing cross-network user behavioral data

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP2643807A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017092342A1 (zh) * 2015-12-02 2017-06-08 乐视控股(北京)有限公司 一种推荐方法和装置
CN111277859A (zh) * 2020-01-15 2020-06-12 腾讯科技(深圳)有限公司 配乐获取方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN103229169B (zh) 2016-06-01
WO2012070880A3 (en) 2012-10-04
JP2014502392A (ja) 2014-01-30
EP2643807A2 (en) 2013-10-02
US9465863B2 (en) 2016-10-11
CN103229169A (zh) 2013-07-31
US20120136861A1 (en) 2012-05-31
KR101802332B1 (ko) 2017-12-29
KR20120076475A (ko) 2012-07-09
EP2643807A4 (en) 2016-08-17
JP5830545B2 (ja) 2015-12-09

Similar Documents

Publication Publication Date Title
WO2012070880A2 (en) Content-providing method and system
CN109074593B (zh) 信息处理装置、信息处理方法、信息处理系统及程序
KR102112973B1 (ko) 컴퓨터 실행 방법, 시스템 및 컴퓨터 판독 가능 매체
US20170091822A1 (en) Electronic digital display screen having a content scheduler operable via a cloud based content management system
US20090271417A1 (en) Identifying User Relationships from Situational Analysis of User Comments Made on Media Content
CN106331779A (zh) 在播放视频过程中基于用户喜好推送主播的方法及系统
US20120102410A1 (en) Media management for multi-user group
KR20050057578A (ko) 상업 광고 추천기
CN109429103B (zh) 推荐信息的方法、装置及计算机可读存储介质、终端设备
JP2002531970A (ja) 加入者識別システム
US20150066897A1 (en) Systems and methods for conveying passive interest classified media content
WO2019132084A1 (ko) 온라인 쇼핑몰 통합 관리 시스템에서의 온라인 판매채널을 추천하는 방법 및 그 서버
Jeong et al. Ontology-based automatic video annotation technique in smart TV environment
KR20100116412A (ko) 동영상 장면 기반 광고정보 제공장치 및 방법
CN109511015A (zh) 多媒体资源推荐方法、装置、存储介质及设备
WO2013168890A1 (ko) 광고 시스템 및 타겟 광고 방법
Chang et al. 3PRS: a personalized popular program recommendation system for digital TV for P2P social networks
Xu et al. Catch-up TV recommendations: show old favourites and find new ones
US20130108180A1 (en) Information processing device, information processing method, and program
WO2014178498A1 (ko) 광고 영상 제작방법 및 이를 위한 제작 시스템과 광고영상이 포함된 영화 파일 제작 시스템 및 영화 파일 제공방법
WO2010098640A2 (ko) 사용자 제어 광고 시스템 및 방법
WO2011059276A2 (en) Method and apparatus for managing content
García-Faura et al. Emotion and attention: Audiovisual models for group-level skin response recognition in short movies
WO2017022880A1 (ko) 영상 콘텐츠와 연관성을 갖는 광고를 제공하기 위한 광고 매칭 시스템 및 방법
WO2019124763A1 (ko) 개인화 홈쇼핑 방송 시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 11842778

Country of ref document: EP

Kind code of ref document: A2

ENP Entry into the national phase in:

Ref document number: 2013539779

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase in:

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2011842778

Country of ref document: EP